So sánh phương pháp
Xem các phương pháp đã chọn cạnh nhau; những hàng khác biệt được làm nổi bật.
| Bộ tự mã hóa biến phân đa ngôn ngữ× | Nhúng câu đa ngôn ngữ× | |
|---|---|---|
| Lĩnh vực | Học sâu | Học sâu |
| Họ | Machine learning | Machine learning |
| Năm ra đời≠ | 2017-2018 | 2019–2022 |
| Người khởi xướng≠ | Multiple research groups (Lample, Conneau et al.; Zhao et al.) | Reimers, N. & Gurevych, I.; Feng, F. et al. (Google) |
| Loại≠ | Generative latent-variable model | Cross-lingual representation learning |
| Công trình gốc≠ | Zhao, T., Zhang, Y., & Eskenazi, M. (2018). Zero-shot dialog generation with cross-domain latent actions. In Proceedings of the 19th Annual SIGdial Meeting on Discourse and Dialogue (pp. 1-10). ACL. link ↗ | Reimers, N. & Gurevych, I. (2020). Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation. Proceedings of EMNLP 2020, 4512–4525. link ↗ |
| Tên gọi khác | ML-VAE, cross-lingual VAE, multilingual latent variable model, multilingual generative autoencoder | multilingual sentence representations, cross-lingual sentence embeddings, mSE, multilingual semantic embeddings |
| Liên quan | 5 | 5 |
| Tóm tắt≠ | A Multilingual Variational Autoencoder (ML-VAE) extends the standard VAE framework to handle multiple languages within a shared probabilistic latent space. Language-specific encoders map text from each language into a common continuous representation, while language-specific decoders reconstruct or translate that text. This enables cross-lingual generation, style transfer, and representation learning with or without parallel corpora. | Multilingual sentence embeddings map sentences from many languages into a single shared vector space so that semantically equivalent sentences — regardless of language — land close together. Models such as LaBSE, multilingual Sentence-BERT, and mUSE have made it practical to compare, retrieve, and classify text across 50 to 100+ languages without translating anything first. |
| ScholarGateBộ dữ liệu ↗ |
|
|